© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 57663
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate comparisons or distinctions between entities or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flèche
    -0.96
     rubrique
    -0.81
     poussière
    -0.79
     poitrine
    -0.78
     mijne
    -0.77
     fumée
    -0.76
     Hawley
    -0.75
     poudre
    -0.73
    arschijnlijk
    -0.70
     virtudes
    -0.67
    POSITIVE LOGITS
     differences
    1.44
     difference
    1.36
     DIFFERENCE
    1.35
     Differences
    1.30
     Difference
    1.22
    difference
    1.22
     DIF
    1.20
    Difference
    1.17
    Differences
    1.16
    differences
    1.13
    Activations Density 0.050%

    No Known Activations